[PATCH] D81411: [ARM][BFloat] Lowering of create/get/set/dup intrinsics

[Mikhail Maltsev via Phabricator via llvm-commits]

miyuki created this revision.
miyuki added reviewers: SjoerdMeijer, dmgreen, labrinea, stuij.
Herald added subscribers: llvm-commits, danielkiss, hiraditya, kristof.beyls.
Herald added a project: LLVM.
miyuki added a parent revision: D81373: [WIP] Basic bfloat support on Arm.

This patch adds codegen for the following BFloat
operations to the ARM backend:

- concatenation of bf16 vectors
- bf16 vector element extraction
- bf16 vector element insertion
- duplication of a bf16 value into each lane of a vector
- duplication of a bf16 vector lane into each lane


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D81411

Files:
  llvm/lib/Target/ARM/ARMInstrNEON.td
  llvm/test/CodeGen/ARM/bf16-create-get-set-dup.ll
  llvm/test/CodeGen/ARM/bf16-getlane-with-fp16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D81411.269280.patch
Type: text/x-patch
Size: 15515 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200608/0d2904ee/attachment.bin>